Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning

Shunfeng Gao; Qinghua Liu; Min Sun; Haoran Zhang

doi:doi:10.11648/j.sd.20251305.13

Research Article |

| Peer-Reviewed

Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning

Shunfeng Gao, Qinghua Liu^*, Min Sun, Haoran Zhang

Published in Science Discovery (Volume 13, Issue 5)

Received: 10 September 2025 Accepted: 11 October 2025 Published: 29 October 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

To address the challenges of low automation and poor adaptability to complex environments in power grid UAV inspections, this study analyzes the architecture and operational constraints of intelligent UAV inspection systems, clarifying optimization goals in terms of efficiency, safety, and intelligence. A closed-loop autonomous flight control method is proposed, integrating high-precision target recognition, dynamic path planning, and reinforcement learning–based optimization. Furthermore, a Transformer-based global obstacle perception and risk assessment approach is designed to construct a holistic “perception–decision–control” technical framework. Field experiments demonstrate that the proposed strategy significantly enhances flight path planning efficiency, obstacle recognition accuracy, and operational safety. The results provide scalable technical support for advancing the digital transformation of power grids and promoting the development of new-type power systems.

Published in	Science Discovery (Volume 13, Issue 5)
DOI	10.11648/j.sd.20251305.13
Page(s)	95-100
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Drone, Obstacle Perception, Intelligent Inspection, Dynamic Path Planning, Reinforcement Learning

References

[1]	高旭东, 张军朝, 张建等.无人机电力线路巡检安全距离测量新方法 [J]. 现代电子技术, 2020, 43(5): 146-149, 154.
[2]	潘翀, 沈鹏飞, 张忠, 等. 基于无人机巡检图像的绝缘子串实时定位研究[J]. 电瓷避雷器, 2020(1): 234-240.
[3]	邵瑰玮, 刘壮, 付晶, 等. 架空输电线路无人机巡检技术研究进展 [J]. 高电压技术, 2020, 46(1): 14-22.
[4]	黄郑, 王永强, 王红星, 等. 基于云雾边异构协同的无人机智慧巡检系统 [J]. 中国电力, 2020, 53(4): 161-168.
[5]	赵太飞, 李晗辰, 张港．无人机巡检电力线放电的紫外探测及定位 [J]. 光学精密工程, 2019, 27(11): 2296-2304.
[6]	郭敬东, 陈彬, 王仁书, 等．基于YOLO的无人机电力线路杆塔巡检图像实时检测 [J]. 中国电力, 2019, 52(7): 17-23.
[7]	曾懿辉, 何通, 郭圣, 等．基于差分定位的输电线路多旋翼无人机智能巡检 [J]. 中国电力, 2019, 52(7): 24-30.
[8]	何晓琴, 吕培庚, 李怀政, 等．基于无人机线路巡视的二次开发应用研究 [J]. 重庆理工大学学报(自然科学), 2018, 32(11): 169-173.
[9]	冯敏, 罗旺, 余磊, 等．适用于无人机巡检图像的输电线路螺栓检测方法 [J]. 电力科学与技术学报, 2018, 33(4): 135-140.
[10]	刘勇, 陈海滨, 刘方．基建现场巡检无人机智能感知系统的研究与应用 [J]. 电力系统保护与控制, 2018, 46(15): 155-161.
[11]	彭向阳, 陈驰, 饶章权, 等. 基于无人机多传感器数据采集的电力线路安全巡检及智能诊断[J]. 高电压技术, 2015, 41(1): 159-166.
[12]	彭继慎, 孙礼鑫, 王凯, 等. 基于模型压缩的ED-YOLO电力巡检无人机避障目标检测算法[J]. 仪器仪表学报, 2023(10): 160-169.
[13]	马瑞, 欧阳权, 吴兆香, 等. 基于深度强化学习的多无人机电力巡检任务规划[J]. 计算机与现代化, 2022(1): 98-102.
[14]	陈博帆, 潘可达, 陈静川, 等. 面向电力巡检场景的多无人机任务分配与路径规划方法[J/OL]. 南方电网技术, 1-9 [2025-01-19].
[15]	Lu M, Fan X, Chen H, et al. Fapp: Fast and adaptive perception and planning for UAVs in dynamic cluttered environments[J]. IEEE Transactions on Robotics, 2025, 41: 871-886.
[16]	Bircher A, Kamel M, Alexis K, et al. Receding horizon "next-best-view" planner for 3d exploration[C]//2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2016: 1462-1468.
[17]	Dang T, Mascarich F, Khattak S, et al. Graph-based path planning for autonomous robotic exploration in subterranean environments [C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019: 3105-3112.

Cite This Article

Plain Text BibTeX RIS

APA Style

Gao, S., Liu, Q., Sun, M., Zhang, H. (2025). Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Science Discovery, 13(5), 95-100. https://doi.org/10.11648/j.sd.20251305.13

Copy | Download

ACS Style

Gao, S.; Liu, Q.; Sun, M.; Zhang, H. Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Sci. Discov. 2025, 13(5), 95-100. doi: 10.11648/j.sd.20251305.13

Copy | Download

AMA Style

Gao S, Liu Q, Sun M, Zhang H. Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Sci Discov. 2025;13(5):95-100. doi: 10.11648/j.sd.20251305.13

Copy | Download

@article{10.11648/j.sd.20251305.13,
  author = {Shunfeng Gao and Qinghua Liu and Min Sun and Haoran Zhang},
  title = {Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning
},
  journal = {Science Discovery},
  volume = {13},
  number = {5},
  pages = {95-100},
  doi = {10.11648/j.sd.20251305.13},
  url = {https://doi.org/10.11648/j.sd.20251305.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20251305.13},
  abstract = {To address the challenges of low automation and poor adaptability to complex environments in power grid UAV inspections, this study analyzes the architecture and operational constraints of intelligent UAV inspection systems, clarifying optimization goals in terms of efficiency, safety, and intelligence. A closed-loop autonomous flight control method is proposed, integrating high-precision target recognition, dynamic path planning, and reinforcement learning–based optimization. Furthermore, a Transformer-based global obstacle perception and risk assessment approach is designed to construct a holistic “perception–decision–control” technical framework. Field experiments demonstrate that the proposed strategy significantly enhances flight path planning efficiency, obstacle recognition accuracy, and operational safety. The results provide scalable technical support for advancing the digital transformation of power grids and promoting the development of new-type power systems.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning

AU  - Shunfeng Gao
AU  - Qinghua Liu
AU  - Min Sun
AU  - Haoran Zhang
Y1  - 2025/10/29
PY  - 2025
N1  - https://doi.org/10.11648/j.sd.20251305.13
DO  - 10.11648/j.sd.20251305.13
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 95
EP  - 100
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20251305.13
AB  - To address the challenges of low automation and poor adaptability to complex environments in power grid UAV inspections, this study analyzes the architecture and operational constraints of intelligent UAV inspection systems, clarifying optimization goals in terms of efficiency, safety, and intelligence. A closed-loop autonomous flight control method is proposed, integrating high-precision target recognition, dynamic path planning, and reinforcement learning–based optimization. Furthermore, a Transformer-based global obstacle perception and risk assessment approach is designed to construct a holistic “perception–decision–control” technical framework. Field experiments demonstrate that the proposed strategy significantly enhances flight path planning efficiency, obstacle recognition accuracy, and operational safety. The results provide scalable technical support for advancing the digital transformation of power grids and promoting the development of new-type power systems.

VL  - 13
IS  - 5
ER  -

Copy | Download

Author Information

Shunfeng Gao

School of Computing, Jiangsu University of Science and Technology, Zhenjiang, China

Contact Email
Qinghua Liu

School of Automation, Jiangsu University of Science and Technology, Zhenjiang, China

Contact Email
Min Sun

School of Automation, Jiangsu University of Science and Technology, Zhenjiang, China

Contact Email
Haoran Zhang

Dental Department, Zhengjiang 359 Hospital, Zhenjiang, China

Contact Email

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Gao, S., Liu, Q., Sun, M., Zhang, H. (2025). Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Science Discovery, 13(5), 95-100. https://doi.org/10.11648/j.sd.20251305.13

Copy | Download

ACS Style

Gao, S.; Liu, Q.; Sun, M.; Zhang, H. Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Sci. Discov. 2025, 13(5), 95-100. doi: 10.11648/j.sd.20251305.13

Copy | Download

AMA Style

Gao S, Liu Q, Sun M, Zhang H. Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning. Sci Discov. 2025;13(5):95-100. doi: 10.11648/j.sd.20251305.13

Copy | Download

@article{10.11648/j.sd.20251305.13,
  author = {Shunfeng Gao and Qinghua Liu and Min Sun and Haoran Zhang},
  title = {Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning
},
  journal = {Science Discovery},
  volume = {13},
  number = {5},
  pages = {95-100},
  doi = {10.11648/j.sd.20251305.13},
  url = {https://doi.org/10.11648/j.sd.20251305.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20251305.13},
  abstract = {To address the challenges of low automation and poor adaptability to complex environments in power grid UAV inspections, this study analyzes the architecture and operational constraints of intelligent UAV inspection systems, clarifying optimization goals in terms of efficiency, safety, and intelligence. A closed-loop autonomous flight control method is proposed, integrating high-precision target recognition, dynamic path planning, and reinforcement learning–based optimization. Furthermore, a Transformer-based global obstacle perception and risk assessment approach is designed to construct a holistic “perception–decision–control” technical framework. Field experiments demonstrate that the proposed strategy significantly enhances flight path planning efficiency, obstacle recognition accuracy, and operational safety. The results provide scalable technical support for advancing the digital transformation of power grids and promoting the development of new-type power systems.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Key Technologies for Target-Driven Autonomous UAV Inspection in Power Grids Based on Reinforcement Learning

AU  - Shunfeng Gao
AU  - Qinghua Liu
AU  - Min Sun
AU  - Haoran Zhang
Y1  - 2025/10/29
PY  - 2025
N1  - https://doi.org/10.11648/j.sd.20251305.13
DO  - 10.11648/j.sd.20251305.13
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 95
EP  - 100
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20251305.13
AB  - To address the challenges of low automation and poor adaptability to complex environments in power grid UAV inspections, this study analyzes the architecture and operational constraints of intelligent UAV inspection systems, clarifying optimization goals in terms of efficiency, safety, and intelligence. A closed-loop autonomous flight control method is proposed, integrating high-precision target recognition, dynamic path planning, and reinforcement learning–based optimization. Furthermore, a Transformer-based global obstacle perception and risk assessment approach is designed to construct a holistic “perception–decision–control” technical framework. Field experiments demonstrate that the proposed strategy significantly enhances flight path planning efficiency, obstacle recognition accuracy, and operational safety. The results provide scalable technical support for advancing the digital transformation of power grids and promoting the development of new-type power systems.

VL  - 13
IS  - 5
ER  -

Copy | Download